R Notebook

candy_2017 %>% 
  get_dupes()

No variable names specified - using all columns.

No duplicate combinations found of: Internal ID, Q1: GOING OUT?, Q2: GENDER, Q3: AGE, Q4: COUNTRY, Q5: STATE, PROVINCE, COUNTY, ETC, Q6 | 100 Grand Bar, Q6 | Anonymous brown globs that come in black and orange wrappers  (a.k.a. Mary Janes), Q6 | Any full-sized candy bar, ... and 111 other variables

# did not use these

candy_2015 <- candy_2015 %>% 
  clean_names() %>% 
  rename(age = "how_old_are_you",
         trick_or_treating = "are_you_going_actually_going_trick_or_treating_yourself",
         brown_globs = "anonymous_brown_globs_that_come_in_black_and_orange_wrappers",
         intravenous_corn_syrup = "vials_of_pure_high_fructose_corn_syrup_for_main_lining_into_your_vein",
         restaurant_candy = "candy_that_is_clearly_just_the_stuff_given_out_for_free_at_restaurants",
         legal_tender = "cash_or_other_forms_of_legal_tender",
         chick_o_sticks = "chick_o_sticks_we_don_t_know_what_that_is")

candy_2016 <- candy_2016 %>% 
  clean_names() %>% 
  rename(age = "how_old_are_you",
         gender = "your_gender",
         trick_or_treating = "are_you_going_actually_going_trick_or_treating_yourself",
         country = "which_country_do_you_live_in",
         state = "which_state_province_county_do_you_live_in",
         intravenous_corn_syrup = "vials_of_pure_high_fructose_corn_syrup_for_main_lining_into_your_vein",
         restaurant_candy = "candy_that_is_clearly_just_the_stuff_given_out_for_free_at_restaurants",
         legal_tender = "cash_or_other_forms_of_legal_tender",
         chick_o_sticks = "chick_o_sticks_we_don_t_know_what_that_is")

candy_2016 <- candy_2016 %>% 
   rename(
     brown_globes = "anonymous_brown_globs_that_come_in_black_and_orange_wrappers"
     )

candy_2017 <- candy_2017 %>% 
  clean_names()

  data_input %>% 
    clean_names() %>%
    remove_empty(which = c("rows", "cols"))

Error in clean_names(.) : object 'data_input' not found

candy_2015 <- clean_tables(candy_2015)
candy_2016 <- clean_tables(candy_2016)
candy_2017 <- clean_tables(candy_2017)

compare_df_cols(candy_2015, candy_2016, return = "match", bind_method = "bind_rows")

combined_candy <- bind_rows(data_2015_2016, candy_2017)

names(combined_candy)
view(combined_candy)

axe all the rows that are not about candy - would give an accurate count of candy ratings

names(combined_candy)

specific_candy_data <- select(combined_candy, -18, -33, -38, -41, -45, -56, -63,
                              -88, -93:-95, -97:-112, -119, -130, -137:-139,
                              -145, -148:-156)

names(specific_candy_data)

## bring all non-candy data to beginning

specific_candy_data <- specific_candy_data %>% 
  select(timestamp:going_out, day:which_state_province_county_do_you_live_in,
         internal_id:state, everything())

## change the values of internal_id and timestamp to just the year


specific_candy_data <- specific_candy_data %>% 
  mutate(timestamp = as.character(timestamp)) %>% 
  mutate(timestamp = if_else(str_detect(timestamp, "2015-+"), "2015", "2016"))

# not sure I need this? 
specific_candy_data %>% 
  rename(year = "timestamp")

specific_candy_data <- specific_candy_data %>% 
  mutate(internal_id = as.character(internal_id)) 

specific_candy_data <- specific_candy_data %>% 
  mutate(internal_id = if_else(str_detect(internal_id, "90+"), "2017", "NO YEAR"))



## merge timestamp and internal_id to create a year column

specific_candy_data <-  specific_candy_data %>% 
  unite("year", timestamp, internal_id, na.rm = TRUE) %>%
  mutate(year = na_if(year, ""))
## dont think i need this bit now
  mutate(year = recode(year, "2015_NA" = "2015", "2016_NA" = "2016", "2017_NA" = "2017"))

#### NEED TO FIX year to not include NA_2017 ####

## merge state with which state... 

specific_candy_data <-  specific_candy_data %>% 
  unite("state_county", state, which_state_province_county_do_you_live_in, na.rm = TRUE) %>% 
  mutate(state_county = na_if(state_county, ""))

specific_candy_data

clean the age column

clean the country column

count all sweet ratings/reviews

• do this by summarise across the columns you want.